Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/14102#discussion_r74380391
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JacksonParser.scala
---
@@ -35,184 +34,296 @@ import org.apache.spark.util.Utils
private[json] class SparkSQLJsonProcessingException(msg: String) extends
RuntimeException(msg)
-object JacksonParser extends Logging {
+class JacksonParser(
+ schema: StructType,
+ columnNameOfCorruptRecord: String,
+ options: JSONOptions) extends Logging {
- def parse(
- input: RDD[String],
- schema: StructType,
- columnNameOfCorruptRecords: String,
- configOptions: JSONOptions): RDD[InternalRow] = {
+ import com.fasterxml.jackson.core.JsonToken._
+
+ // A `ValueConverter` is responsible for converting a value from
`JsonParser`
+ // to a value in a field for `InternalRow`.
+ private type ValueConverter = (JsonParser) => Any
+
+ // `ValueConverter`s for the root schema for all fields in the schema
+ private val rootConverter: ValueConverter = makeRootConverter(schema)
- input.mapPartitions { iter =>
- parseJson(iter, schema, columnNameOfCorruptRecords, configOptions)
+ private val factory = new JsonFactory()
+ options.setJacksonOptions(factory)
+
+ /**
+ * This function deals with the cases it fails to parse. This function
will be called
+ * when exceptions are caught during converting. This functions also
deals with `mode` option.
+ */
+ private def failedRecord(record: String): Seq[InternalRow] = {
+ // create a row even if no corrupt record column is present
+ if (options.failFast) {
+ throw new RuntimeException(s"Malformed line in FAILFAST mode:
$record")
+ }
+ if (options.dropMalformed) {
+ logWarning(s"Dropping malformed line: $record")
+ Nil
+ } else {
+ val row = new GenericMutableRow(schema.length)
+ for (corruptIndex <-
schema.getFieldIndex(columnNameOfCorruptRecord)) {
+ require(schema(corruptIndex).dataType == StringType)
+ row.update(corruptIndex, UTF8String.fromString(record))
+ }
+ Seq(row)
}
}
/**
- * Parse the current token (and related children) according to a desired
schema
- * This is a wrapper for the method `convertField()` to handle a row
wrapped
- * with an array.
+ * This function will be called afterward except the case for
`StringType`. we
+ * throw an exception when it is failed unless the value is null.
*/
- def convertRootField(
- factory: JsonFactory,
+ private def failedConversion(
parser: JsonParser,
- schema: DataType): Any = {
- import com.fasterxml.jackson.core.JsonToken._
- (parser.getCurrentToken, schema) match {
- case (START_ARRAY, st: StructType) =>
- // SPARK-3308: support reading top level JSON arrays and take
every element
- // in such an array as a row
- convertArray(factory, parser, st)
-
- case (START_OBJECT, ArrayType(st, _)) =>
+ dataType: DataType): PartialFunction[JsonToken, Any] = {
+ case VALUE_STRING if parser.getTextLength < 1 =>
+ // If conversion is failed, this produces `null` rather than
+ // rather than throw exception. This will protect the mismatch of
types.
+ null
+
+ case token =>
+ // We cannot parse this token based on the given data type. So, we
throw a
+ // SparkSQLJsonProcessingException and this exception will be caught
by
+ // `parse` method.
+ throw new SparkSQLJsonProcessingException(
+ s"Failed to parse a value for data type $dataType (current token:
$token).")
+ }
+
+ /**
+ * Create a converter which converts the JSON documents held by the
`JsonParser`
+ * to a value according to a desired schema. This is a wrapper for the
method
+ * `makeConverter()` to handle a row wrapped with an array.
+ */
+ def makeRootConverter(dataType: DataType): ValueConverter = dataType
match {
--- End diff --
the previous `convertRootField` only handles the special cases:
(START_ARRAY, StructType) and (START_OBJECT, ArrayType). Can we follow that
logic here?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
